The 4th Conference on Digital Preservation and processing technology of Written Heritage  will be held within the IEEE CiSt’2025 international congress the week of 04th - 10th October 2025, Ouarzazate - Marrakech, Morocco.

Preservation, accessibility and exploration of written heritage are core tasks of cultural institutions such as galleries, libraries, archives, and museums (aka GLAM institutions) as well as of universities and other research organizations. Digital technologies provide cutting-edge and comprehensive approaches to safeguard texts and historical documents more effectively as well as to enable meaningful engagement with written heritage by scholars, local communities and the general public.

Artificial Intelligence enhancements in digitization technologies and computational systems have been proposed adopting machine learning and deep learning approaches facilitating workflows and analytic tasks.This technical progress allows for considerable advances in classification strategies, automated text recognition, reconstruction of fragments and damaged documents, information extraction, analysis and interpretation of documents and textual resources at large scale. However, the transformation of textual heritage into digital assets gives rise to many concerns and challenges. The loss of information issue from acquisition of an original object and the efficient management in terms of sustainability and accessibility of large textual traditions from many documents written in many languages are but two of many problems to handle.

New opportunities offered by implementing and using Large Language Models (LLMs), such as GPT or LLAMA models, pose methodological and theoretical implications concerning traditional ways of perceiving and defining texts and textuality, including means and mechanisms of textual transmission. Digitally transformed ecosystems of knowledge are based on the digital representations of texts and text bearing objects, with the potential of allowing a more efficient preservation and, potentially, a more accurate comprehension of their history and tradition which may help to better understand the present and plan for the future.

The conference aims to serve as a valuable venue for researchers and practitioners to exchange their insights, experiences, and best practices. The conference will focus on various aspects related to the preservation strategies and workflows, digital content management and automatic processing environments as well as infrastructures, frameworks and tools used for preserving, analyzing and making accessible written heritage.

We solicit submissions of original case studies and papers describing significant empirical and theoretical studies on the digitization of written heritage and the digital transformation of societies and cultural heritage organizations. Topics covered include but not restricted to the following areas and interdisciplinary fields:

• Digitisation workflows, tools and infrastructures

  • Digital archives, libraries and editions

  • Born digital textual heritage

  • Heritagization criteria and practices

  • Knowledge representation: accumulation, integration, management

  • Accessibility, usability, impact and sustainability of digital resources

  • Digital standards and formats for textual representation

  • Annotation, indexing and search

  • Licenses and legal issues

• AI, Machine Learning and Deep Learning approaches to textual heritage

  • Generative AI for written heritage studies

  • Large Language Models for under-represented languages and scripts

  • Layout analysis and classification

  • Automated Text Recognition (ATR)

  • Multimodality and audiovisual mediality

  • Textual authenticity, fidelity and reliability